Exception
1 year ago
Inflector
1 year ago
Resources
1 year ago
Slugger
1 year ago
AbstractString.php
1 year ago
AbstractUnicodeString.php
1 year ago
ByteString.php
1 year ago
CHANGELOG.md
1 year ago
CodePointString.php
1 year ago
LICENSE
1 year ago
LazyString.php
1 year ago
README.md
1 year ago
UnicodeString.php
1 year ago
composer.json
1 year ago
UnicodeString.php
378 lines
| 1 | <?php |
| 2 | |
| 3 | /* |
| 4 | * This file is part of the Symfony package. |
| 5 | * |
| 6 | * (c) Fabien Potencier <fabien@symfony.com> |
| 7 | * |
| 8 | * For the full copyright and license information, please view the LICENSE |
| 9 | * file that was distributed with this source code. |
| 10 | */ |
| 11 | |
| 12 | namespace Symfony\Component\String; |
| 13 | |
| 14 | use Symfony\Component\String\Exception\ExceptionInterface; |
| 15 | use Symfony\Component\String\Exception\InvalidArgumentException; |
| 16 | |
| 17 | /** |
| 18 | * Represents a string of Unicode grapheme clusters encoded as UTF-8. |
| 19 | * |
| 20 | * A letter followed by combining characters (accents typically) form what Unicode defines |
| 21 | * as a grapheme cluster: a character as humans mean it in written texts. This class knows |
| 22 | * about the concept and won't split a letter apart from its combining accents. It also |
| 23 | * ensures all string comparisons happen on their canonically-composed representation, |
| 24 | * ignoring e.g. the order in which accents are listed when a letter has many of them. |
| 25 | * |
| 26 | * @see https://unicode.org/reports/tr15/ |
| 27 | * |
| 28 | * @author Nicolas Grekas <p@tchwork.com> |
| 29 | * @author Hugo Hamon <hugohamon@neuf.fr> |
| 30 | * |
| 31 | * @throws ExceptionInterface |
| 32 | */ |
| 33 | class UnicodeString extends AbstractUnicodeString |
| 34 | { |
| 35 | public function __construct(string $string = '') |
| 36 | { |
| 37 | $this->string = normalizer_is_normalized($string) ? $string : normalizer_normalize($string); |
| 38 | |
| 39 | if (false === $this->string) { |
| 40 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
| 41 | } |
| 42 | } |
| 43 | |
| 44 | public function append(string ...$suffix): AbstractString |
| 45 | { |
| 46 | $str = clone $this; |
| 47 | $str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix)); |
| 48 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 49 | |
| 50 | if (false === $str->string) { |
| 51 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
| 52 | } |
| 53 | |
| 54 | return $str; |
| 55 | } |
| 56 | |
| 57 | public function chunk(int $length = 1): array |
| 58 | { |
| 59 | if (1 > $length) { |
| 60 | throw new InvalidArgumentException('The chunk length must be greater than zero.'); |
| 61 | } |
| 62 | |
| 63 | if ('' === $this->string) { |
| 64 | return []; |
| 65 | } |
| 66 | |
| 67 | $rx = '/('; |
| 68 | while (65535 < $length) { |
| 69 | $rx .= '\X{65535}'; |
| 70 | $length -= 65535; |
| 71 | } |
| 72 | $rx .= '\X{'.$length.'})/u'; |
| 73 | |
| 74 | $str = clone $this; |
| 75 | $chunks = []; |
| 76 | |
| 77 | foreach (preg_split($rx, $this->string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY) as $chunk) { |
| 78 | $str->string = $chunk; |
| 79 | $chunks[] = clone $str; |
| 80 | } |
| 81 | |
| 82 | return $chunks; |
| 83 | } |
| 84 | |
| 85 | public function endsWith($suffix): bool |
| 86 | { |
| 87 | if ($suffix instanceof AbstractString) { |
| 88 | $suffix = $suffix->string; |
| 89 | } elseif (\is_array($suffix) || $suffix instanceof \Traversable) { |
| 90 | return parent::endsWith($suffix); |
| 91 | } else { |
| 92 | $suffix = (string) $suffix; |
| 93 | } |
| 94 | |
| 95 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
| 96 | normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form); |
| 97 | |
| 98 | if ('' === $suffix || false === $suffix) { |
| 99 | return false; |
| 100 | } |
| 101 | |
| 102 | if ($this->ignoreCase) { |
| 103 | return 0 === mb_stripos(grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)), $suffix, 0, 'UTF-8'); |
| 104 | } |
| 105 | |
| 106 | return $suffix === grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)); |
| 107 | } |
| 108 | |
| 109 | public function equalsTo($string): bool |
| 110 | { |
| 111 | if ($string instanceof AbstractString) { |
| 112 | $string = $string->string; |
| 113 | } elseif (\is_array($string) || $string instanceof \Traversable) { |
| 114 | return parent::equalsTo($string); |
| 115 | } else { |
| 116 | $string = (string) $string; |
| 117 | } |
| 118 | |
| 119 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
| 120 | normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form); |
| 121 | |
| 122 | if ('' !== $string && false !== $string && $this->ignoreCase) { |
| 123 | return \strlen($string) === \strlen($this->string) && 0 === mb_stripos($this->string, $string, 0, 'UTF-8'); |
| 124 | } |
| 125 | |
| 126 | return $string === $this->string; |
| 127 | } |
| 128 | |
| 129 | public function indexOf($needle, int $offset = 0): ?int |
| 130 | { |
| 131 | if ($needle instanceof AbstractString) { |
| 132 | $needle = $needle->string; |
| 133 | } elseif (\is_array($needle) || $needle instanceof \Traversable) { |
| 134 | return parent::indexOf($needle, $offset); |
| 135 | } else { |
| 136 | $needle = (string) $needle; |
| 137 | } |
| 138 | |
| 139 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
| 140 | normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
| 141 | |
| 142 | if ('' === $needle || false === $needle) { |
| 143 | return null; |
| 144 | } |
| 145 | |
| 146 | try { |
| 147 | $i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset); |
| 148 | } catch (\ValueError $e) { |
| 149 | return null; |
| 150 | } |
| 151 | |
| 152 | return false === $i ? null : $i; |
| 153 | } |
| 154 | |
| 155 | public function indexOfLast($needle, int $offset = 0): ?int |
| 156 | { |
| 157 | if ($needle instanceof AbstractString) { |
| 158 | $needle = $needle->string; |
| 159 | } elseif (\is_array($needle) || $needle instanceof \Traversable) { |
| 160 | return parent::indexOfLast($needle, $offset); |
| 161 | } else { |
| 162 | $needle = (string) $needle; |
| 163 | } |
| 164 | |
| 165 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
| 166 | normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
| 167 | |
| 168 | if ('' === $needle || false === $needle) { |
| 169 | return null; |
| 170 | } |
| 171 | |
| 172 | $string = $this->string; |
| 173 | |
| 174 | if (0 > $offset) { |
| 175 | // workaround https://bugs.php.net/74264 |
| 176 | if (0 > $offset += grapheme_strlen($needle)) { |
| 177 | $string = grapheme_substr($string, 0, $offset); |
| 178 | } |
| 179 | $offset = 0; |
| 180 | } |
| 181 | |
| 182 | $i = $this->ignoreCase ? grapheme_strripos($string, $needle, $offset) : grapheme_strrpos($string, $needle, $offset); |
| 183 | |
| 184 | return false === $i ? null : $i; |
| 185 | } |
| 186 | |
| 187 | public function join(array $strings, ?string $lastGlue = null): AbstractString |
| 188 | { |
| 189 | $str = parent::join($strings, $lastGlue); |
| 190 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 191 | |
| 192 | return $str; |
| 193 | } |
| 194 | |
| 195 | public function length(): int |
| 196 | { |
| 197 | return grapheme_strlen($this->string); |
| 198 | } |
| 199 | |
| 200 | /** |
| 201 | * @return static |
| 202 | */ |
| 203 | public function normalize(int $form = self::NFC): parent |
| 204 | { |
| 205 | $str = clone $this; |
| 206 | |
| 207 | if (\in_array($form, [self::NFC, self::NFKC], true)) { |
| 208 | normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form); |
| 209 | } elseif (!\in_array($form, [self::NFD, self::NFKD], true)) { |
| 210 | throw new InvalidArgumentException('Unsupported normalization form.'); |
| 211 | } elseif (!normalizer_is_normalized($str->string, $form)) { |
| 212 | $str->string = normalizer_normalize($str->string, $form); |
| 213 | $str->ignoreCase = null; |
| 214 | } |
| 215 | |
| 216 | return $str; |
| 217 | } |
| 218 | |
| 219 | public function prepend(string ...$prefix): AbstractString |
| 220 | { |
| 221 | $str = clone $this; |
| 222 | $str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string; |
| 223 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 224 | |
| 225 | if (false === $str->string) { |
| 226 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
| 227 | } |
| 228 | |
| 229 | return $str; |
| 230 | } |
| 231 | |
| 232 | public function replace(string $from, string $to): AbstractString |
| 233 | { |
| 234 | $str = clone $this; |
| 235 | normalizer_is_normalized($from) ?: $from = normalizer_normalize($from); |
| 236 | |
| 237 | if ('' !== $from && false !== $from) { |
| 238 | $tail = $str->string; |
| 239 | $result = ''; |
| 240 | $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
| 241 | |
| 242 | while ('' !== $tail && false !== $i = $indexOf($tail, $from)) { |
| 243 | $slice = grapheme_substr($tail, 0, $i); |
| 244 | $result .= $slice.$to; |
| 245 | $tail = substr($tail, \strlen($slice) + \strlen($from)); |
| 246 | } |
| 247 | |
| 248 | $str->string = $result.$tail; |
| 249 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 250 | |
| 251 | if (false === $str->string) { |
| 252 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
| 253 | } |
| 254 | } |
| 255 | |
| 256 | return $str; |
| 257 | } |
| 258 | |
| 259 | public function replaceMatches(string $fromRegexp, $to): AbstractString |
| 260 | { |
| 261 | $str = parent::replaceMatches($fromRegexp, $to); |
| 262 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 263 | |
| 264 | return $str; |
| 265 | } |
| 266 | |
| 267 | public function slice(int $start = 0, ?int $length = null): AbstractString |
| 268 | { |
| 269 | $str = clone $this; |
| 270 | |
| 271 | if (\PHP_VERSION_ID < 80000 && 0 > $start && grapheme_strlen($this->string) < -$start) { |
| 272 | $start = 0; |
| 273 | } |
| 274 | $str->string = (string) grapheme_substr($this->string, $start, $length ?? 2147483647); |
| 275 | |
| 276 | return $str; |
| 277 | } |
| 278 | |
| 279 | public function splice(string $replacement, int $start = 0, ?int $length = null): AbstractString |
| 280 | { |
| 281 | $str = clone $this; |
| 282 | |
| 283 | if (\PHP_VERSION_ID < 80000 && 0 > $start && grapheme_strlen($this->string) < -$start) { |
| 284 | $start = 0; |
| 285 | } |
| 286 | $start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0; |
| 287 | $length = $length ? \strlen(grapheme_substr($this->string, $start, $length ?? 2147483647)) : $length; |
| 288 | $str->string = substr_replace($this->string, $replacement, $start, $length ?? 2147483647); |
| 289 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
| 290 | |
| 291 | if (false === $str->string) { |
| 292 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
| 293 | } |
| 294 | |
| 295 | return $str; |
| 296 | } |
| 297 | |
| 298 | public function split(string $delimiter, ?int $limit = null, ?int $flags = null): array |
| 299 | { |
| 300 | if (1 > $limit = $limit ?? 2147483647) { |
| 301 | throw new InvalidArgumentException('Split limit must be a positive integer.'); |
| 302 | } |
| 303 | |
| 304 | if ('' === $delimiter) { |
| 305 | throw new InvalidArgumentException('Split delimiter is empty.'); |
| 306 | } |
| 307 | |
| 308 | if (null !== $flags) { |
| 309 | return parent::split($delimiter.'u', $limit, $flags); |
| 310 | } |
| 311 | |
| 312 | normalizer_is_normalized($delimiter) ?: $delimiter = normalizer_normalize($delimiter); |
| 313 | |
| 314 | if (false === $delimiter) { |
| 315 | throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.'); |
| 316 | } |
| 317 | |
| 318 | $str = clone $this; |
| 319 | $tail = $this->string; |
| 320 | $chunks = []; |
| 321 | $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
| 322 | |
| 323 | while (1 < $limit && false !== $i = $indexOf($tail, $delimiter)) { |
| 324 | $str->string = grapheme_substr($tail, 0, $i); |
| 325 | $chunks[] = clone $str; |
| 326 | $tail = substr($tail, \strlen($str->string) + \strlen($delimiter)); |
| 327 | --$limit; |
| 328 | } |
| 329 | |
| 330 | $str->string = $tail; |
| 331 | $chunks[] = clone $str; |
| 332 | |
| 333 | return $chunks; |
| 334 | } |
| 335 | |
| 336 | public function startsWith($prefix): bool |
| 337 | { |
| 338 | if ($prefix instanceof AbstractString) { |
| 339 | $prefix = $prefix->string; |
| 340 | } elseif (\is_array($prefix) || $prefix instanceof \Traversable) { |
| 341 | return parent::startsWith($prefix); |
| 342 | } else { |
| 343 | $prefix = (string) $prefix; |
| 344 | } |
| 345 | |
| 346 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
| 347 | normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form); |
| 348 | |
| 349 | if ('' === $prefix || false === $prefix) { |
| 350 | return false; |
| 351 | } |
| 352 | |
| 353 | if ($this->ignoreCase) { |
| 354 | return 0 === mb_stripos(grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES), $prefix, 0, 'UTF-8'); |
| 355 | } |
| 356 | |
| 357 | return $prefix === grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES); |
| 358 | } |
| 359 | |
| 360 | public function __wakeup() |
| 361 | { |
| 362 | if (!\is_string($this->string)) { |
| 363 | throw new \BadMethodCallException('Cannot unserialize '.__CLASS__); |
| 364 | } |
| 365 | |
| 366 | normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
| 367 | } |
| 368 | |
| 369 | public function __clone() |
| 370 | { |
| 371 | if (null === $this->ignoreCase) { |
| 372 | normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
| 373 | } |
| 374 | |
| 375 | $this->ignoreCase = false; |
| 376 | } |
| 377 | } |
| 378 |